通过反事实推理解释 $\boldsymbol{\u2113\u210b}$ 概念描述
Explaining $\mathcal{ELH}$ Concept Descriptions through Counterfactual Reasoning
AI总结：
针对知识库与描述逻辑 $\u2113\u210b$ 中概念描述难以被非专业人士理解的问题，本文提出基于最小特征改变的反事实解释方法，并通过用户调研验证了候选项的偏好性。
摘要：
知识库被广泛应用于信息管理领域，支撑着网页搜索、问答系统、自然语言处理等高影响力应用，同时也是医疗诊断、信用评分等自动决策系统的核心支柱。由于受这些决策影响的利益相关方希望了解自身处境、验证决策的公平性，学界已提出多种解释方法。使用描述逻辑中的概念进行分类是一种本质上具备可解释性的方式，但这些概念可能冗长复杂，即便经过言语化表述，非专业人士也难以理解。\n一种解决方案是采用反事实来回答“必须如何改变特征值才能得到不同的分类结果？”这一问题。通过聚焦最小程度的特征改变，这类解释简洁易懂、符合人类认知习惯，还能为预测结果的改变提供清晰的行动路径。此前的研究多针对表格数据探索反事实方法，本文则将反事实的概念迁移至知识库与描述逻辑 $\u2113\u210b$ 场景中。\n本文方法首先从概念生成反事实候选项，随后筛选出所需特征改变最少的候选项作为反事实；若存在多个反事实，则根据其特征组合的合理性进行排序。研究通过开展用户调研评估方法效果，以确定参与者更偏好哪些反事实候选项作为解释。
英文摘要：
Knowledge bases are widely used for information management, enabling high-impact applications such as web search, question answering, and natural language processing. They also serve as the backbone for automatic decision systems, e.g., for medical diagnostics and credit scoring. As stakeholders affected by these decisions would like to understand their situation and verify how fair the decisions are, a number of explanation approaches have been proposed. An intrinsically transparent way to do classification is by using concepts in description logics. However, these concepts can become long and difficult to fathom for non-experts, even when verbalized. One solution is to employ counterfactuals to answer the question, ``How must feature values be changed to obtain a different classification?'' By focusing on the minimal feature changes, the explanations are short, human-friendly, and provide a clear path of action regarding the change in prediction. While previous work investigated counterfactuals for tabular data, in this paper, we transfer the notion of counterfactuals to knowledge bases and the description logic $\mathcal{ELH}$. Our approach starts by generating counterfactual candidates from concepts, followed by selecting the candidates requiring the fewest feature changes as counterfactuals. When multiple counterfactuals exist, we rank them based on the likeliness of their feature combinations. We evaluate our method by conducting a user survey to determine which counterfactual candidates participants prefer for explanation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
